Skip to content

CoverCraft AI by Ambuj Kumar Tripathi

by Ambuj123-lab · remote · no sign-in to list tools · v1.0.0 · published by GitHub user Ambuj123-lab

Live Hugging Face model proofing, ATS resume scoring and career tools by Ambuj Kumar Tripathi

Changes · 4
CompareRegistry entry

8 tools: 4 change things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http covercraft https://career-workspace-ambujsystems.vercel.app/api/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Changes things 4Claude Code: ask
  • ats_readinessPerform heuristic ATS compliance checks (keyword coverage, word count, metrics density, parseable formatting, contact info).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Perform heuristic ATS compliance checks (keyword coverage, word count, metrics density, parseable formatting, contact info).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • cover_letter_generatorSynthesize structured, evidence-grounded cover letter paragraphs with in-line citations and tone alignment.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Synthesize structured, evidence-grounded cover letter paragraphs with in-line citations and tone alignment.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • jd_analyzerParse target Job Description and match required skills against candidate experience with evidence classification and gap detection.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Parse target Job Description and match required skills against candidate experience with evidence classification and gap detection.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • source_filterAudit and categorize research source domains into authoritative tiers (Tier 1: Official/SEC, Tier 2: Reputable tech press, Tier 3: Aggregators) and discard promotional spam.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Audit and categorize research source domains into authoritative tiers (Tier 1: Official/SEC, Tier 2: Reputable tech press, Tier 3: Aggregators) and discard promotional spam.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Claude Code: allow
  • company_researchSearch web for verified company information, tech stack, and engineering culture using Tavily API and grounded synthesis.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Search web for verified company information, tech stack, and engineering culture using Tavily API and grounded synthesis.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • evidence_validatorValidate factual resume claims against verified web source citations using deterministic Claim Ledger verification.No findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate factual resume claims against verified web source citations using deterministic Claim Ledger verification. Rejects unsupported claims.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • github_prooferInspect public GitHub repositories, code languages, commit activity, stars, and forks to fact-check candidate technical claims.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "inspect" and "repository": it reads repositories.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Inspect public GitHub repositories, code languages, commit activity, stars, and forks to fact-check candidate technical claims. Validates evidence-backed claims and flags uncorroborated technical claims.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • huggingface_prooferInspect public Hugging Face assets (models, spaces, datasets, lifetime and rolling 30-day downloads) to verify GenAI, LoRA, GGUF, and LLM fine-tuning claims.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Inspect public Hugging Face assets (models, spaces, datasets, lifetime and rolling 30-day downloads) to verify GenAI, LoRA, GGUF, and LLM fine-tuning claims.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http covercraft https://career-workspace-ambujsystems.vercel.app/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__covercraft__company_research",
      "mcp__covercraft__evidence_validator",
      "mcp__covercraft__github_proofer",
      "mcp__covercraft__huggingface_proofer"
    ],
    "ask": [
      "mcp__covercraft__jd_analyzer",
      "mcp__covercraft__ats_readiness",
      "mcp__covercraft__source_filter",
      "mcp__covercraft__cover_letter_generator"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as covercraft. Review it before you use it.

Capability tags behind 4 rules
  • mcp__covercraft__company_research untrusted-input
  • mcp__covercraft__cover_letter_generator untrusted-input
  • mcp__covercraft__github_proofer private-data, untrusted-input
  • mcp__covercraft__huggingface_proofer untrusted-input